Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1270 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2533. Min Range: -2.2533

Max Act: 2.2533. Min Act: -0.0000

Data Index: 1188411 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 2.2533. Min Range: -2.2533

Max Act: 2.1389. Min Act: -0.0000

Data Index: 267080 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.8945. Min Act: -0.0000

Data Index: 775728 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.8038. Min Act: -0.0000

Data Index: 635386 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.7289. Min Act: -0.0000

Data Index: 203980 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.6129. Min Act: -0.0000

Data Index: 901647 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.7042. Min Act: -0.0000

Data Index: 740183 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.5053. Min Act: -0.0000

Data Index: 294904 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.4874. Min Act: -0.0000

Data Index: 107301 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.6190. Min Act: -0.0000

Data Index: 140599 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.5323. Min Act: -0.0000

Data Index: 169374 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1090750 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.4715. Min Act: -0.0000

Data Index: 947407 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.3769. Min Act: -0.0000

Data Index: 1027487 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.5439. Min Act: -0.0000

Data Index: 292264 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.4016. Min Act: -0.0000

Data Index: 1023476 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.4333. Min Act: -0.0000

Data Index: 460097 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.5137. Min Act: -0.0000

Data Index: 928928 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.4507. Min Act: -0.0000

Data Index: 845577 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 2.2533. Min Range: -2.2533

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1108005 (C4 (Web Text))

Max Activating Token Index: 576